summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorSteven Rostedt <srostedt@redhat.com>2012-06-07 11:54:37 -0400
committerSteven Rostedt <rostedt@goodmis.org>2012-06-08 18:51:12 -0400
commit70fb74a5420f9caa3e001d65004e4b669124283e (patch)
treea099c86b2e63dc5d6246b8efe07a5b3e91b1301e
parentc7d65a78fc18ed70353baeb7497ec71a7c775ac5 (diff)
downloadop-kernel-dev-70fb74a5420f9caa3e001d65004e4b669124283e.zip
op-kernel-dev-70fb74a5420f9caa3e001d65004e4b669124283e.tar.gz
x86: Save cr2 in NMI in case NMIs take a page fault (for i386)
Avi Kivity reported that page faults in NMIs could cause havic if the NMI preempted another page fault handler: The recent changes to NMI allow exceptions to take place in NMI handlers, but I think that a #PF (say, due to access to vmalloc space) is still problematic. Consider the sequence #PF (cr2 set by processor) NMI ... #PF (cr2 clobbered) do_page_fault() IRET ... IRET do_page_fault() address = read_cr2() The last line reads the overwritten cr2 value. This is the i386 version, which has the luxury of doing the work in C code. Link: http://lkml.kernel.org/r/4FBB8C40.6080304@redhat.com Reported-by: Avi Kivity <avi@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
-rw-r--r--arch/x86/kernel/nmi.c12
1 files changed, 12 insertions, 0 deletions
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index a15a888..f84f5c5 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -395,6 +395,14 @@ static __kprobes void default_do_nmi(struct pt_regs *regs)
* thus there is no race between the first check of state for NOT_RUNNING
* and setting it to NMI_EXECUTING. The HW will prevent nested NMIs
* at this point.
+ *
+ * In case the NMI takes a page fault, we need to save off the CR2
+ * because the NMI could have preempted another page fault and corrupt
+ * the CR2 that is about to be read. As nested NMIs must be restarted
+ * and they can not take breakpoints or page faults, the update of the
+ * CR2 must be done before converting the nmi state back to NOT_RUNNING.
+ * Otherwise, there would be a race of another nested NMI coming in
+ * after setting state to NOT_RUNNING but before updating the nmi_cr2.
*/
enum nmi_states {
NMI_NOT_RUNNING = 0,
@@ -402,6 +410,7 @@ enum nmi_states {
NMI_LATCHED,
};
static DEFINE_PER_CPU(enum nmi_states, nmi_state);
+static DEFINE_PER_CPU(unsigned long, nmi_cr2);
#define nmi_nesting_preprocess(regs) \
do { \
@@ -410,11 +419,14 @@ static DEFINE_PER_CPU(enum nmi_states, nmi_state);
return; \
} \
this_cpu_write(nmi_state, NMI_EXECUTING); \
+ this_cpu_write(nmi_cr2, read_cr2()); \
} while (0); \
nmi_restart:
#define nmi_nesting_postprocess() \
do { \
+ if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \
+ write_cr2(this_cpu_read(nmi_cr2)); \
if (this_cpu_dec_return(nmi_state)) \
goto nmi_restart; \
} while (0)
OpenPOWER on IntegriCloud